--- title: Final Project - National Sites and Gas Prices author: Esther Goldberg and Anna Poon date: 'December 8th, 2022' format: html: code-fold: true ---

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px

parks = pd.read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-09-17/national_parks.csv")
gas = pd.read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-09-17/gas_price.csv")
pop = pd.read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-09-17/state_pop.csv")
parks = parks[parks["year"].str.contains("Total")==False]
parks["year"] = parks.year.astype("int")
locations = pd.read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-09-17/locations.csv")

parks.year.min()

1904

ranks = pd.DataFrame(parks.groupby(by=["unit_name","region"]).visitors.sum()).reset_index()
ranks = ranks.sort_values(by="visitors", ascending=False)
partial = ranks[["unit_name", "visitors"]].head(5)
partial

	unit_name	visitors
33	Blue Ridge Parkway	871922828.0
152	Golden Gate National Recreation Area	611031225.0
162	Great Smoky Mountains National Park	521947058.0
253	Natchez Trace Parkway	443145232.0
213	Lake Mead National Recreation Area	411700377.0

bypark = parks[["unit_name","year","visitors"]]
bypark = bypark.merge(partial, how="right", on="unit_name")
bypark = bypark.rename(columns={"visitors_x":"Visitors", "visitors_y":"Visitors (All-Time)","unit_name":"Park Name"})
bypark = bypark.sort_values(by="year")
bypark.head(3)

	Park Name	year	Visitors	Visitors (All-Time)
120	Great Smoky Mountains National Park	1931	154000.0	521947058.0
205	Great Smoky Mountains National Park	1932	300000.0	521947058.0
204	Great Smoky Mountains National Park	1933	375000.0	521947058.0

fig = px.line(bypark, x='year', y='Visitors', 
              title='Number of Visitors Per Year at the Five Most Visited US National Parks (1931-2016)',color="Park Name")

fig.update_xaxes(rangeslider_visible=True)
fig.show(renderer='notebook')

fig.write_html("fig1_line.html")

Figure 2: This graph represents the number of visitors over time

Line graph showing the trends in yearly visitor numbers at the five most popular US national parks. All five sites show a clear increase in visitors over time, although some sites were built after the records were created (Golden Gate National Recreation Area was built in the 1970s). Data

import descartes
import geopandas as geo
from shapely.geometry import Point, Polygon

%matplotlib inline
earth = geo.read_file(geo.datasets.get_path('naturalearth_lowres'))

park = parks[['year','gnis_id','parkname','region','state','unit_name','unit_type','visitors']]
parks = park.merge(locations, on='gnis_id', how='left')
parks = parks[(parks['lon'] != (parks.lon.max())) & (parks['year'] != 'Total')]
parks = parks.sort_values(by='year')
parks = 

fig = px.scatter_mapbox(parks, lon="lon", lat="lat", animation_frame="year", \
                        color="visitors", hover_name="unit_name", hover_data=["visitors"],\
                        zoom=2)

fig["layout"].pop("updatemenus") # optional, drop animation buttons
fig.update_layout(mapbox_style="open-street-map", 
                  margin={"r":0,"t":60,"l":0,"b":0},
                  title_text='Number of Visitors at US National Sites from 1929 to 2016')

fig.show(renderer='notebook')

fig.write_html("fig2_map.html")

parks = pd.read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-09-17/national_parks.csv")
parks = parks[parks["year"].str.contains("Total")==False]
parks["year"] = parks.year.astype("int")

import plotly.io as pio
import plotly.express as px

plt.rcParams.update({'font.size': 13})

plt.figure(figsize=(12,7))
sns.set_style("whitegrid")
    #"darkgrid", {"axes.facecolor": ".9"})

sns.lineplot(data=gas, x='year', y='gas_current', label = 'Current (Nominal)', color='red')
sns.lineplot(data=gas, x='year', y='gas_constant', label = 'Constant (Real)', color='orange')

plt.title('Average Gas Prices in the US from 1929 to 2016', pad=10)
plt.xlabel('Year', labelpad=10)
plt.ylabel('Price (US Dollars)', labelpad=10)

print()

plt.savefig("fig3_gas.jpeg")

poptot = pop.groupby(by="year")["pop"].sum()
poptot = pd.DataFrame(poptot).reset_index()
merge = parks.merge(gas, how="right", on="year")
totals = parks.groupby(by="year")["visitors"].sum()
totals = pd.DataFrame(totals).reset_index()
totals = totals.merge(gas, how="inner", on="year")
totals = totals.merge(poptot, how="inner", on="year")
totals["Visits per Capita"] = totals["visitors"] / totals["pop"]
totals = totals.rename(columns={"gas_constant": "Constant Gas Price ($ per gallon)", "year": "Year"})

#sns.scatterplot(data=totals, x="gas_current", y="percap", label="Nominal Dollars")
import plotly.io as pio
import plotly.express as px

fig = px.scatter(totals, x="Constant Gas Price ($ per gallon)", y="Visits per Capita", color="Year", 
                 title="Gas Prices vs. Number of Visits to US National Sites per Capita from 1929 to 2015",
                color_continuous_scale = ["#5CDA56", "#4DC8C3", "#322FCB", "#B838F4", "#F79DDC"])

fig1 = px.line(totals, x="Constant Gas Price ($ per gallon)", y="Visits per Capita")

pio.templates.default="plotly_white"

fig.show(renderer='notebook')

fig.write_html("fig4_scatter.html")

print()

popyear = pd.DataFrame(pop.groupby(by="year").pop.sum()).reset_index()
df = pd.DataFrame(parks.groupby(by="year").visitors.sum()).reset_index()
popyear = popyear.merge(df, how="inner", on="year")
popyear = popyear.rename(columns={"year": "Year"})
popyear["pop"] = popyear["pop"]/1000000
popyear["visitors"] = popyear["visitors"]/1000000
popyear.head(3)

	Year	pop	visitors
0	1904	82.165	0.120690
1	1905	83.818	0.140954
2	1906	85.439	0.030569

plt.rcParams.update({'font.size': 15})

plt.figure(figsize=(12,7))
sns.set_style("whitegrid")
    #"darkgrid", {"axes.facecolor": ".9"})

fig = sns.scatterplot(data=popyear, x='pop', y='visitors', hue='Year', palette="winter")


plt.title('Visitors to National Parks vs. US Population (1904-2015)', pad=10)
plt.xlabel('US Population (Millions)', labelpad=10)
plt.ylabel('Visitors to National Parks (Millions)', labelpad=10)

print()

plt.savefig("fig5_pop.jpeg")